© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71031
    Prev
    Next
    INDEX
    Explanations

    geographic locations and directions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to numeric figures and quantities (standalone numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    archical
    -1.36
     INFORMACIÓN
    -1.34
    軼
    -1.31
    notations
    -1.30
     (~(
    -1.25
    secutive
    -1.24
     salmón
    -1.23
     mangiare
    -1.22
    sements
    -1.22
     {$\
    -1.21
    POSITIVE LOGITS
    vaila
    1.28
    complished
    1.19
    nachron
    1.16
     around
    1.14
     vagyok
    1.13
     from
    1.11
    ülle
    1.08
    capace
    1.05
     south
    1.05
     South
    1.05
    Activations Density 0.091%

    No Known Activations